dataframely 1.13.0__tar.gz → 1.14.0__tar.gz

{dataframely-1.13.0 → dataframely-1.14.0}/.github/workflows/build.yml

@@ -13,11 +13,11 @@ jobs:
     permissions:
       contents: read
     steps:
-      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+      - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
         with:
           fetch-depth: 0
       - name: Set up pixi
-        uses: prefix-dev/setup-pixi@8ca4608ef7f4daeb54f5205b20d0b7cb42f11143 # v0.8.14
+        uses: prefix-dev/setup-pixi@194d461b21b6c5717c722ffc597fa91ed2ff29fa # v0.9.1
         with:
           environments: build
       - name: Set version
@@ -48,17 +48,17 @@ jobs:
           - target-platform: win-64
             os: windows-latest
     steps:
-      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+      - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
         with:
           fetch-depth: 0
       - name: Set up pixi
-        uses: prefix-dev/setup-pixi@8ca4608ef7f4daeb54f5205b20d0b7cb42f11143 # v0.8.14
+        uses: prefix-dev/setup-pixi@194d461b21b6c5717c722ffc597fa91ed2ff29fa # v0.9.1
         with:
           environments: build
       - name: Set version
         run: pixi run -e build set-version
       - name: Build wheel
-        uses: PyO3/maturin-action@e10f6c464b90acceb5f640d31beda6d586ba7b4a # v1.49.3
+        uses: PyO3/maturin-action@86b9d133d34bc1b40018696f782949dac11bd380 # v1.49.4
         with:
           command: build
           args: --out dist -i python3.10
@@ -80,9 +80,9 @@ jobs:
       id-token: write
     environment: pypi
     steps:
-      - uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093 # v4.3.0
+      - uses: actions/download-artifact@634f93cb2916e3fdff6788551b99b062d0335ce0 # v5.0.0
         with:
           path: dist
           merge-multiple: true
       - name: Publish package on PyPi
-        uses: pypa/gh-action-pypi-publish@76f52bc884231f62b9a034ebfe128415bbaabdfc # v1.12.4
+        uses: pypa/gh-action-pypi-publish@ed0c53931b1dc9bd32cbe73a98c7f6766f8a527e # v1.13.0

{dataframely-1.13.0 → dataframely-1.14.0}/.github/workflows/chore.yml

@@ -21,7 +21,7 @@ jobs:
     steps:
       - name: Check valid conventional commit message
         id: lint
-        uses: amannn/action-semantic-pull-request@0723387faaf9b38adef4775cd42cfd5155ed6017 # v5.5.3
+        uses: amannn/action-semantic-pull-request@48f256284bd46cdaab1048c3721360e808335d50 # v6.1.1
         with:
           subjectPattern: ^[A-Z].+[^. ]$ # subject must start with uppercase letter and may not end with a dot/space
         env:

{dataframely-1.13.0 → dataframely-1.14.0}/.github/workflows/ci.yml

@@ -19,12 +19,12 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout branch
-        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+        uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
         with:
           # needed for 'pre-commit-mirrors-insert-license'
           fetch-depth: 0
       - name: Set up pixi
-        uses: prefix-dev/setup-pixi@8ca4608ef7f4daeb54f5205b20d0b7cb42f11143 # v0.8.14
+        uses: prefix-dev/setup-pixi@194d461b21b6c5717c722ffc597fa91ed2ff29fa # v0.9.1
         with:
           environments: default lint
       - name: Install repository
@@ -51,9 +51,9 @@ jobs:
             with_optionals: true
     steps:
       - name: Checkout branch
-        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+        uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
       - name: Set up pixi
-        uses: prefix-dev/setup-pixi@8ca4608ef7f4daeb54f5205b20d0b7cb42f11143 # v0.8.14
+        uses: prefix-dev/setup-pixi@194d461b21b6c5717c722ffc597fa91ed2ff29fa # v0.9.1
         with:
           environments: ${{ matrix.environment }}
       - name: Install repository
@@ -61,7 +61,7 @@ jobs:
       - name: Run pytest
         run: pixi run -e ${{ matrix.environment }} test-coverage --color=yes ${{ matrix.with_optionals && '-m with_optionals' || '-m "not with_optionals"'}} --cov=dataframely --cov-report=xml
       - name: Upload codecov
-        uses: codecov/codecov-action@18283e04ce6e62d37312384ff67231eb8fd56d24 # v5.4.3
+        uses: codecov/codecov-action@5a1091511ad55cbe89839c7260b706298ca349f7 # v5.5.1
         with:
           files: ./coverage.xml
           token: ${{ secrets.CODECOV_TOKEN }}

{dataframely-1.13.0 → dataframely-1.14.0}/.github/workflows/nightly.yml

@@ -23,9 +23,9 @@ jobs:
         os: [ubuntu-latest, windows-latest]
     steps:
       - name: Checkout branch
-        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+        uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
       - name: Set up pixi
-        uses: prefix-dev/setup-pixi@8ca4608ef7f4daeb54f5205b20d0b7cb42f11143 # v0.8.14
+        uses: prefix-dev/setup-pixi@194d461b21b6c5717c722ffc597fa91ed2ff29fa # v0.9.1
         with:
           environments: nightly
       - name: Install polars nightly

{dataframely-1.13.0 → dataframely-1.14.0}/.github/workflows/scorecard.yml

@@ -35,12 +35,12 @@ jobs:
 
     steps:
       - name: "Checkout code"
-        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+        uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
         with:
           persist-credentials: false
 
       - name: "Run analysis"
-        uses: ossf/scorecard-action@05b42c624433fc40578a4040d5cf5e36ddca8cde # v2.4.2
+        uses: ossf/scorecard-action@4eaacf0543bb3f2c246792bd56e8cdeffafb205a # v2.4.3
         with:
           results_file: results.sarif
           results_format: sarif
@@ -74,6 +74,6 @@ jobs:
       # Upload the results to GitHub's code scanning dashboard (optional).
       # Commenting out will disable upload of results to your repo's Code Scanning dashboard
       - name: "Upload to code-scanning"
-        uses: github/codeql-action/upload-sarif@51f77329afa6477de8c49fc9c7046c15b9a4e79d # v3.29.5
+        uses: github/codeql-action/upload-sarif@3599b3baa15b485a2e49ef411a7a4bb2452e7f93 # v3.29.5
         with:
           sarif_file: results.sarif

{dataframely-1.13.0 → dataframely-1.14.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dataframely
-Version: 1.13.0
+Version: 1.14.0
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11

{dataframely-1.13.0 → dataframely-1.14.0}/dataframely/_base_schema.py

@@ -137,6 +137,29 @@ class SchemaMeta(ABCMeta):
                         f"which are not in the schema: {missing_list}."
                     )
 
+        # 3) Check that all members are non-pathological (i.e., user errors).
+        for attr, value in namespace.items():
+            if attr.startswith("__"):
+                continue
+            # Check for tuple of column (commonly caused by trailing comma)
+            if (
+                isinstance(value, tuple)
+                and len(value) > 0
+                and isinstance(value[0], Column)
+            ):
+                raise TypeError(
+                    f"Column '{attr}' is defined as a tuple of dy.Column. "
+                    f"Did you accidentally add a trailing comma?"
+                )
+
+            # Check for column type instead of instance (e.g., dy.Float64 instead of dy.Float64())
+            if isinstance(value, type) and issubclass(value, Column):
+                raise TypeError(
+                    f"Column '{attr}' is a type, not an instance. "
+                    f"Schema members must be of type Column not type[Column]. "
+                    f"Did you forget to add parentheses?"
+                )
+
         return super().__new__(mcs, name, bases, namespace, *args, **kwargs)
 
     def __getattribute__(cls, name: str) -> Any:

{dataframely-1.13.0 → dataframely-1.14.0}/dataframely/columns/_mixins.py

@@ -76,7 +76,7 @@ class OrdinalMixin(Generic[T], Base):
             result["min_exclusive"] = expr > self.min_exclusive  # type: ignore
         if self.max is not None:
             result["max"] = expr <= self.max  # type: ignore
-        if self.max_exclusive:
+        if self.max_exclusive is not None:
             result["max_exclusive"] = expr < self.max_exclusive  # type: ignore
         return result
 

{dataframely-1.13.0 → dataframely-1.14.0}/docs/_api/dataframely.columns.rst

@@ -25,6 +25,14 @@ dataframely.columns.array module
    :show-inheritance:
    :undoc-members:
 
+dataframely.columns.binary module
+---------------------------------
+
+.. automodule:: dataframely.columns.binary
+   :members:
+   :show-inheritance:
+   :undoc-members:
+
 dataframely.columns.bool module
 -------------------------------
 
@@ -33,6 +41,14 @@ dataframely.columns.bool module
    :show-inheritance:
    :undoc-members:
 
+dataframely.columns.categorical module
+--------------------------------------
+
+.. automodule:: dataframely.columns.categorical
+   :members:
+   :show-inheritance:
+   :undoc-members:
+
 dataframely.columns.datetime module
 -----------------------------------
 

{dataframely-1.13.0 → dataframely-1.14.0}/docs/_api/dataframely.testing.rst

@@ -41,6 +41,14 @@ dataframely.testing.rules module
    :show-inheritance:
    :undoc-members:
 
+dataframely.testing.storage module
+----------------------------------
+
+.. automodule:: dataframely.testing.storage
+   :members:
+   :show-inheritance:
+   :undoc-members:
+
 dataframely.testing.typing module
 ---------------------------------
 

{dataframely-1.13.0 → dataframely-1.14.0}/docs/index.rst

@@ -22,11 +22,12 @@ Contents
 
 .. toctree::
     :caption: Contents
-    :maxdepth: 1
+    :maxdepth: 2
 
     Installation <sites/installation.rst>
     Quickstart <sites/quickstart.rst>
     Real-world Example <sites/examples/real-world.ipynb>
+    Features <sites/features/index.rst>
     FAQ <sites/faq.rst>
     Development Guide <sites/development.rst>
     Versioning <sites/versioning.rst>

dataframely-1.14.0/docs/sites/faq.rst

@@ -0,0 +1,30 @@
+FAQ
+===
+
+Whenever you find out something that you were surprised by or needed some non-trivial
+thinking, please add it here.
+
+How do I define additional unique keys in a ``dy.Schema``?
+----------------------------------------------------------
+
+By default, ``dataframely`` only supports defining a single non-nullable (composite) primary key in ``dy.Schema``.
+However, in some scenarios it may be useful to define additional unique keys (which support nullable fields and/or which are additionally unique).
+
+Consider the following example, which demonstrates two rules: one for validating that a field is entirely unique, and another for validating that a field, when provided, is unique.
+
+::
+
+    class UserSchema(dy.Schema):
+        user_id = dy.UInt64(primary_key=True, nullable=False)
+        username = dy.String(nullable=False)
+        email = dy.String(nullable=True)  # Must be unique, or null.
+
+        @dy.rule(group_by=["username"])
+        def unique_username() -> pl.Expr:
+            """Username, a non-nullable field, must be total unique."""
+            return pl.len() == 1
+
+        @dy.rule()
+        def unique_email_or_null() -> pl.Expr:
+            """Email must be unique, if provided."""
+            return pl.col("email").is_null() | pl.col("email").is_unique()

dataframely-1.14.0/docs/sites/features/index.rst

@@ -0,0 +1,7 @@
+Features
+========
+
+.. toctree::
+    :maxdepth: 1
+
+   primary-keys.rst

dataframely-1.14.0/docs/sites/features/primary-keys.rst

@@ -0,0 +1,47 @@
+Primary keys
+============
+
+Defining primary keys in ``dy.Schema``
+--------------------------------------
+
+When working with tabular data, it is often useful to define a `primary key <https://en.wikipedia.org/wiki/Primary_key>`_. A primary key is a set of one or multiple column, the combined values of which form a unique identifier for every record in a table.
+
+Dataframely supports marking columns as part of the primary key when defining a ``dy.Schema`` by setting ``primary_key=True`` on the respective column(s).
+
+.. note::
+
+  Primary key columns must not be nullable.
+
+Single primary keys
+^^^^^^^^^^^^^^^^^^^
+
+For example, when managing data about users, we might use an ``id`` column to uniquely identify users:
+
+::
+
+    class UserSchema(dy.Schema):
+      name = dy.String(primary_key=True)
+      name = dy.String()
+
+When we later validate data with this schema, ``dataframely`` checks that the values of the primary key are unique, i.e. there are no two users with the same value of ``id``. Having multiple users with the same ``name`` but different ``id`` but be allowed in this case.
+
+Composite primary keys
+^^^^^^^^^^^^^^^^^^^^^^
+
+In another scenario, we might be tracking line items on invoices. We have many invoices, and each invoice may contain any number of line items. To uniquely identify a line item, we need to specify the invoice, as well as the line items position within the invoice. To encode this, we set ``primary_key=True`` on both the ``invoice_id`` and ``item_id`` columns:
+
+::
+
+    class LineItemSchema(dy.Schema):
+      invoice_id = dy.Int64(primary_key=True)
+      item_id = dy.Int64(primary_key=True)
+      price = dy.Decimal()
+
+Validation will now ensure that all pairs of (``invoice_id``, ``item_id``) are unique.
+
+
+Primary keys in ``dy.Collection``
+---------------------------------
+
+The central idea behind ``dy.Collection`` is to unify multiple tables relating to the same set of underlying entities.
+This is useful because it allows us to write ``dy.filter``s that use information from multiple tables to identify whether the underlying entity is valid or not. If any ``dy.filter``s are defined, ``dataframely`` requires the tables in a ``dy.Collection`` to have an overlapping primary key (i.e., there must be at least one column that is a primary key in all tables).